def __init__()

in convit.py [0:0]

• 41 lines of code
• 8 McCabe index (conditional complexity)

    def __init__(self, img_size=224, patch_size=16, in_chans=3, num_classes=1000, embed_dim=48, depth=12,
                 num_heads=12, mlp_ratio=4., qkv_bias=False, qk_scale=None, drop_rate=0., attn_drop_rate=0.,
                 drop_path_rate=0., hybrid_backbone=None, norm_layer=nn.LayerNorm, global_pool=None,
                 local_up_to_layer=10, locality_strength=1., use_pos_embed=True):
        super().__init__()
        self.num_classes = num_classes
        self.local_up_to_layer = local_up_to_layer
        self.num_features = self.embed_dim = embed_dim  # num_features for consistency with other models
        self.locality_strength = locality_strength
        self.use_pos_embed = use_pos_embed

        if hybrid_backbone is not None:
            self.patch_embed = HybridEmbed(
                hybrid_backbone, img_size=img_size, in_chans=in_chans, embed_dim=embed_dim)
        else:
            self.patch_embed = PatchEmbed(
                img_size=img_size, patch_size=patch_size, in_chans=in_chans, embed_dim=embed_dim)
        num_patches = self.patch_embed.num_patches
        self.num_patches = num_patches
        
        self.cls_token = nn.Parameter(torch.zeros(1, 1, embed_dim))
        self.pos_drop = nn.Dropout(p=drop_rate)

        if self.use_pos_embed:
            self.pos_embed = nn.Parameter(torch.zeros(1, num_patches, embed_dim))
            trunc_normal_(self.pos_embed, std=.02)

        dpr = [x.item() for x in torch.linspace(0, drop_path_rate, depth)]  # stochastic depth decay rule
        self.blocks = nn.ModuleList([
            Block(
                dim=embed_dim, num_heads=num_heads, mlp_ratio=mlp_ratio, qkv_bias=qkv_bias, qk_scale=qk_scale,
                drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[i], norm_layer=norm_layer,
                use_gpsa=True,
                locality_strength=locality_strength)
            if i<local_up_to_layer else
            Block(
                dim=embed_dim, num_heads=num_heads, mlp_ratio=mlp_ratio, qkv_bias=qkv_bias, qk_scale=qk_scale,
                drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[i], norm_layer=norm_layer,
                use_gpsa=False)
            for i in range(depth)])
        self.norm = norm_layer(embed_dim)

        # Classifier head
        self.feature_info = [dict(num_chs=embed_dim, reduction=0, module='head')]
        self.head = nn.Linear(embed_dim, num_classes) if num_classes > 0 else nn.Identity()

        trunc_normal_(self.cls_token, std=.02)
        self.head.apply(self._init_weights)